Emma Borgström presents her master's thesis
	
Wind speed modeling and simulation for application on the Nordic power market

Abstract

The purpose of this master thesis is to simulate yearlong synthetic
time series of wind speed. To achieve this observed wind speed data
from Schleswig in northern Germany is investigated and
modelled. Before the actual modelling takes place several basic
features of wind speed data, including non-Gaussian distribution and
yearly and diurnal nonstationarity, is taken into account. The
positive correlation between consecutive wind speed observations is
taken into account by fitting an autoregressive process to wind speed
transformed to make their distribution approximately Gaussian and
standardized to remove any nonstationary behaviour. As a result
simulation of wind speed series with the same statistical properties
as the observed wind speed in Schleswig are created.